# 3D OCT Volume Synthesis on OCTA-500 (test)

Source: [3D OCT Volume Synthesis on OCTA-500 (test)](<https://www.sota2.com/research/sota/3d-oct-volume-synthesis-on-octa-500-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:47:17.681Z

Evaluation of 3D OCT Volume Synthesis performance on the test split of the OCTA-500 dataset, using generative quality metrics like Intra-FID, Inter-FID, and Total Variation (TV).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | 3D OCT Volume Synthesis |
| Dataset (including any stated split) | OCTA-500 (test) |
| Metric | Intra-FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Intra-FID](<https://www.sota2.com/research/sota/3d-oct-volume-synthesis-on-octa-500-test.md?metric=Intra-FID>): Lower is better; unit: SCALAR.

- [Inter-FID](<https://www.sota2.com/research/sota/3d-oct-volume-synthesis-on-octa-500-test.md?metric=Inter-FID>): Lower is better; unit: SCALAR.

- [TV](<https://www.sota2.com/research/sota/3d-oct-volume-synthesis-on-octa-500-test.md?metric=TV>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Intra-FID | Result date | Report paper |
| --- | --- | --- | --- |
| CA-LDM | 17.1 | Not recorded | 68fa734d1e209131cea5ba6f |
| NHAE + Diff3D + Diffslice | 17.69 | Not recorded | 68fa734d1e209131cea5ba6f |
| LVD | 21.78 | Not recorded | 68fa734d1e209131cea5ba6f |
| NHAE + Diff3D | 39.06 | Not recorded | 68fa734d1e209131cea5ba6f |
| Medical Diffusion | 48.9 | Not recorded | 68fa734d1e209131cea5ba6f |
| LDM3D | 97.62 | Not recorded | 68fa734d1e209131cea5ba6f |

### CA-LDM

Intra-FID: 17.1. Result ID: 6992d1013a6c31484911b158.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Implementation](<https://github.com/nicetomeetu21/CA-LDM>)

Recorded evaluation configuration: {"Components":"NHAE, Diff3D, Diffslice, DECM"}. This record does not assert independent reproduction.

### NHAE + Diff3D + Diffslice

Intra-FID: 17.69. Result ID: 6992d1013a6c31484911b157.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Implementation](<https://github.com/nicetomeetu21/CA-LDM>)

Recorded evaluation configuration: {"Components":"NHAE, Diff3D, Diffslice"}. This record does not assert independent reproduction.

### LVD

Intra-FID: 21.78. Result ID: 6992d1013a6c31484911b155.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa719f1e209131cea52224.md>)

[Implementation](<https://research.nvidia.com/labs/toronto-ai/VideoLDM/>)

Recorded evaluation configuration: {"Type":"Latent Video Diffusion"}. This record does not assert independent reproduction.

### NHAE + Diff3D

Intra-FID: 39.06. Result ID: 6992d1013a6c31484911b156.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Implementation](<https://github.com/nicetomeetu21/CA-LDM>)

Recorded evaluation configuration: {"Components":"NHAE, Diff3D"}. This record does not assert independent reproduction.

### Medical Diffusion

Intra-FID: 48.9. Result ID: 6992d1013a6c31484911b154.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e471e209131cea3ee65.md>)

Recorded evaluation configuration: {"Autoencoder":"3D"}. This record does not assert independent reproduction.

### LDM3D

Intra-FID: 97.62. Result ID: 6992d1013a6c31484911b153.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5ba6f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c391e209131cea32e4a.md>)

[Implementation](<https://github.com/CompVis/latent-diffusion>)

Recorded evaluation configuration: {"Autoencoder":"2D"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.